RT info:eu-repo/semantics/conferenceObject
T1 Automated detection of childhood sleep apnea using discrete wavelet transform of nocturnal oximetry and anthropometric variables
A1 Crespo Senado, Andrea
A1 Vaquerizo Villar, Fernando
A1 Álvarez González, Daniel
A1 Gutiérrez Tobal, Gonzalo César
A1 Barroso García, Verónica
A1 Cerezo Hernández, Ana
A1 López Muñiz, Graciela
A1 Kheirandish Gozal, Leila
A1 Gozal, David
A1 Hornero Sánchez, Roberto
A1 Campo Matias, Félix del
AB Background. Standard pediatric in-lab polysomnography (PSG) isrelatively unavailable and particularly intrusive for children. In low resourcesettings, nocturnal oximetry has been proposed as a feasible andpotentially reliable screening tool for childhood obstructive sleep apneahypopneasyndrome (OSAHS), although additional confirmatory evidence isneeded.Aims and objectives. Discrete wavelet transform (DWT) could be a usefultool to characterize fluctuations in nocturnal oximetry. We aimed atdesigning and assessing a model for detecting childhood OSAHS usinganthropometric and DWT features.Methods. A total of 298 children with clinical suspicion of OSAHSunderwent in-lab PSG. A cut-off of 5 events/h was stipulated as confirmingOSAHS. DWT was used to inspect the spectral content of oximetry infrequency bands linked with apnea pseudo-periodicity: detail levels D9(0.024-0.049 Hz) and D10 (0.012-0.024 Hz). Mean, variance, minimum, and maximum of DWT coefficients were computed. Stepwise logistic regressionwas employed to build an OSAHS model from DWT, age, gender, and bodymass index (BMI) z score. Training (60%) and test (40%) sets wererandomly allocated.Results. Age, gender, D9 mean, and D10 variance were automaticallyselected. Our model reached 79.1% sensitivity, 81.7% specificity, 4.33 LR+,0.26 LR-, and 80.5% accuracy in the test set.Conclusions. Features from DWT coefficients and anthropometricvariables such as age provide complementary information that enablesdetection of moderate-to-severe childhood OSAHS in a high pre-testprobability cohort.
YR 2017
FD 2017
LK http://uvadoc.uva.es/handle/10324/31357
UL http://uvadoc.uva.es/handle/10324/31357
LA eng
NO Producción Científica
DS UVaDOC
RD 23-nov-2024